According to the self-teaching hypothesis (Share, 1995), word-specific orthographic representations are acquired primarily as a result of the self-teaching opportunities provided by the phonological recoding of novel letter strings. This hypothesis was tested by asking normal second graders to read aloud short texts containing embedded pseudoword targets. Three days later, target spellings were correctly identified more often, named more quickly, and spelled more accurately than alternate homophonic spellings. Experiment 2 examined whether this rapid orthographic learning can be attributed to mere visual exposure to target strings. It was found that viewing the target letter strings under conditions designed to minimize phonological processing significantly attenuated orthographic learning. Experiment 3 went on to show that this reduced orthographic learning was not attributable to alternative nonphonological factors (brief exposure durations or decontextualized presentation). The results of a fourth experiment suggested that the contribution of pure visual exposure to orthographic learning is marginal. It was concluded that phonological recoding is critical to the acquisition of word-specific orthographic representations as proposed by the self-teaching hypothesis. Copyright 1999 Academic Press.